© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 28625
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Safety
    -0.08
     uncomfort
    -0.07
     unnamed
    -0.07
     liable
    -0.07
    Typ
    -0.07
    aining
    -0.07
     repository
    -0.07
     transformers
    -0.07
     condemning
    -0.06
     distract
    -0.06
    POSITIVE LOGITS
     Lahore
    0.07
     nuestra
    0.07
    مفا
    0.07
    ריש
    0.07
     Shaw
    0.07
    Warm
    0.06
    */,↵
    0.06
    вар
    0.06
    华盛
    0.06
    :"",↵
    0.06
    Activations Density 0.022%

    No Known Activations